© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4360
    Prev
    Next
    INDEX
    Explanations

    offering help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    7
    2.72
    6
    2.36
    rinsic
    2.35
    8
    2.32
     deportes
    2.26
     Respir
    2.13
    ۷
    2.12
    5
    2.12
     Entities
    2.09
    ٧
    2.09
    POSITIVE LOGITS
     ante
    1.20
     adjournment
    1.18
     orthodont
    1.18
    ………….
    1.17
    他在
    1.15
     速
    1.15
     odometer
    1.13
     îl
    1.13
    筵
    1.12
     both
    1.11
    Activations Density 0.100%

    No Known Activations